Security audit

read-image

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it helps describe user-supplied images by sending selected image files to an OpenRouter vision model.

Install only if you are comfortable sending selected images to OpenRouter-backed vision models. Avoid using it on sensitive photos, private documents, or images with confidential metadata unless you have reviewed the files and accepted that external processing.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs the agent to send local image files to an external OpenRouter-hosted vision model via `opencode run --file`, but it does not clearly require an explicit user warning or consent step before transmission. Images often contain sensitive visual content or embedded metadata, so silent delegation to a third-party service can expose private data beyond the user's expectations.

Static analysis

No suspicious patterns detected.